A Bayesian Approach for Selective Image-Based Rendering using Superpixels

Abstract : Image-Based Rendering (IBR) algorithms generate high quality photo-realistic imagery without the burden of detailed modeling and expensive realistic rendering. Recent methods have different strengths and weaknesses, depending on 3D reconstruction quality and scene content. Each algorithm operates with a set of hypotheses about the scene and the novel views, resulting in different quality/speed trade-offs in different image regions. We present a principled approach to select the algorithm with the best quality/speed trade-off in each region. To do this, we propose a Bayesian approach, modeling the rendering quality, the rendering process and the validity of the assumptions of each algorithm. We then choose the algorithm to use with Maximum a Posteriori estimation. We demonstrate the utility of our approach on recent IBR algorithms which use oversegmentation and are based on planar reprojection and shape-preserving warps respectively. Our algorithm selects the best rendering algorithm for each superpixel in a preprocessing step; at runtime our selective IBR uses this choice to achieve significant speedup at equivalent or better quality compared to previous algorithms.
Type de document :
Communication dans un congrès
International Conference on 3D Vision - 3DV, Oct 2015, Lyon, France. International Conference on 3D Vision - 3DV
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01207907
Contributeur : Team Reves <>
Soumis le : vendredi 2 octobre 2015 - 22:00:42
Dernière modification le : lundi 9 avril 2018 - 15:23:37
Document(s) archivé(s) le : dimanche 3 janvier 2016 - 10:14:02

Fichier

Ortiz-Cayon_3DV2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01207907, version 1

Collections

Citation

Rodrigo Ortiz-Cayon, Abdelaziz Djelouah, George Drettakis. A Bayesian Approach for Selective Image-Based Rendering using Superpixels. International Conference on 3D Vision - 3DV, Oct 2015, Lyon, France. International Conference on 3D Vision - 3DV. 〈hal-01207907〉

Partager

Métriques

Consultations de la notice

300

Téléchargements de fichiers

400